© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98502
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron chiefly detects numeric tokens (digits and number-related symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nước
    -1.02
     DELLE
    -1.00
    sieht
    -0.98
     odpad
    -0.93
    
    -0.92
    ί
    -0.92
    ₓ
    -0.92
    šov
    -0.91
     Ná
    -0.91
    ³/
    -0.91
    POSITIVE LOGITS
     your
    1.38
     you
    1.13
    етесь
    1.13
    まれて
    1.11
    ena
    1.09
     مجتمع
    1.06
     utveck
    1.02
    ✚
    1.02
     paltry
    1.00
    に加
    1.00
    Activations Density 0.001%

    No Known Activations